diff mbox series

[bpf-next,16/19] af_unix: implement unix_dgram_bpf_recvmsg()

Message ID 20210203041636.38555-17-xiyou.wangcong@gmail.com (mailing list archive)
State Changes Requested
Delegated to: BPF
Headers show
Series sock_map: add non-TCP and cross-protocol support | expand

Checks

Context Check Description
netdev/cover_letter success Link
netdev/fixes_present success Link
netdev/patch_count fail Series longer than 15 patches
netdev/tree_selection success Clearly marked for bpf-next
netdev/subject_prefix success Link
netdev/cc_maintainers warning 14 maintainers not CCed: gustavoars@kernel.org jingxiangfeng@huawei.com songliubraving@fb.com pabeni@redhat.com andrii@kernel.org jbi.octave@gmail.com cai@lca.pw kpsingh@kernel.org ktkhai@virtuozzo.com davem@davemloft.net ast@kernel.org kuba@kernel.org kafai@fb.com yhs@fb.com
netdev/source_inline success Was 0 now: 0
netdev/verify_signedoff success Link
netdev/module_param success Was 0 now: 0
netdev/build_32bit fail Errors and warnings before: 79 this patch: 79
netdev/kdoc success Errors and warnings before: 0 this patch: 0
netdev/verify_fixes success Link
netdev/checkpatch warning WARNING: line length of 83 exceeds 80 columns
netdev/build_allmodconfig_warn fail Errors and warnings before: 78 this patch: 78
netdev/header_inline success Link
netdev/stable success Stable not CCed

Commit Message

Cong Wang Feb. 3, 2021, 4:16 a.m. UTC 
From: Cong Wang <cong.wang@bytedance.com>

We have to implement unix_dgram_bpf_recvmsg() to replace the
original ->recvmsg() to retrieve skmsg from ingress_msg.

AF_UNIX is again special here because the lack of
sk_prot->recvmsg(). I simply add a special case inside
unix_dgram_recvmsg() to call sk->sk_prot->recvmsg() directly.

Cc: John Fastabend <john.fastabend@gmail.com>
Cc: Daniel Borkmann <daniel@iogearbox.net>
Cc: Jakub Sitnicki <jakub@cloudflare.com>
Cc: Lorenz Bauer <lmb@cloudflare.com>
Signed-off-by: Cong Wang <cong.wang@bytedance.com>
---
 include/net/af_unix.h |  3 +++
 net/unix/af_unix.c    | 21 ++++++++++++++++---
 net/unix/unix_bpf.c   | 49 +++++++++++++++++++++++++++++++++++++++++++
 3 files changed, 70 insertions(+), 3 deletions(-)
diff mbox series

Patch

diff --git a/include/net/af_unix.h b/include/net/af_unix.h
index fa75f899e88a..f6c43667e995 100644
--- a/include/net/af_unix.h
+++ b/include/net/af_unix.h
@@ -82,6 +82,9 @@  static inline struct unix_sock *unix_sk(const struct sock *sk)
 long unix_inq_len(struct sock *sk);
 long unix_outq_len(struct sock *sk);
 
+int __unix_dgram_recvmsg(struct sock *sk, struct msghdr *msg, size_t size,
+			 int nonblock, int flags, int *addr_len);
+
 #ifdef CONFIG_SYSCTL
 int unix_sysctl_register(struct net *net);
 void unix_sysctl_unregister(struct net *net);
diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c
index 21c4406f879b..eebcd6f7ef88 100644
--- a/net/unix/af_unix.c
+++ b/net/unix/af_unix.c
@@ -2094,11 +2094,11 @@  static void unix_copy_addr(struct msghdr *msg, struct sock *sk)
 	}
 }
 
-static int unix_dgram_recvmsg(struct socket *sock, struct msghdr *msg,
-			      size_t size, int flags)
+int __unix_dgram_recvmsg(struct sock *sk, struct msghdr *msg, size_t size,
+			 int nonblock, int flags, int *addr_len)
 {
 	struct scm_cookie scm;
-	struct sock *sk = sock->sk;
+	struct socket *sock = sk->sk_socket;
 	struct unix_sock *u = unix_sk(sk);
 	struct sk_buff *skb, *last;
 	long timeo;
@@ -2201,6 +2201,21 @@  static int unix_dgram_recvmsg(struct socket *sock, struct msghdr *msg,
 	return err;
 }
 
+static int unix_dgram_recvmsg(struct socket *sock, struct msghdr *msg, size_t size,
+			      int flags)
+{
+	struct sock *sk = sock->sk;
+	int addr_len = 0;
+
+#ifdef CONFIG_BPF_SOCK_MAP
+	if (sk->sk_prot != &unix_proto)
+		return sk->sk_prot->recvmsg(sk, msg, size, flags & MSG_DONTWAIT,
+					    flags & ~MSG_DONTWAIT, &addr_len);
+#endif
+	return __unix_dgram_recvmsg(sk, msg, size, flags & MSG_DONTWAIT,
+				    flags, &addr_len);
+}
+
 int unix_read_sock(struct sock *sk, read_descriptor_t *desc,
 		   sk_read_actor_t recv_actor)
 {
diff --git a/net/unix/unix_bpf.c b/net/unix/unix_bpf.c
index 2e6a26ec4958..570261fd18cd 100644
--- a/net/unix/unix_bpf.c
+++ b/net/unix/unix_bpf.c
@@ -5,6 +5,54 @@ 
 #include <net/sock.h>
 #include <net/af_unix.h>
 
+static int unix_dgram_bpf_recvmsg(struct sock *sk, struct msghdr *msg,
+				  size_t len, int nonblock, int flags,
+				  int *addr_len)
+{
+	struct sk_psock *psock;
+	int copied, ret;
+
+	psock = sk_psock_get(sk);
+	if (unlikely(!psock))
+		return __unix_dgram_recvmsg(sk, msg, len, nonblock, flags,
+					    addr_len);
+
+	lock_sock(sk);
+	if (!skb_queue_empty(&sk->sk_receive_queue) &&
+	    sk_psock_queue_empty(psock)) {
+		ret = __unix_dgram_recvmsg(sk, msg, len, nonblock, flags,
+					   addr_len);
+		goto out;
+	}
+
+msg_bytes_ready:
+	copied = sk_msg_recvmsg(sk, psock, msg, len, flags);
+	if (!copied) {
+		int data, err = 0;
+		long timeo;
+
+		timeo = sock_rcvtimeo(sk, nonblock);
+		data = sk_msg_wait_data(sk, psock, flags, timeo, &err);
+		if (data) {
+			if (!sk_psock_queue_empty(psock))
+				goto msg_bytes_ready;
+			ret = __unix_dgram_recvmsg(sk, msg, len, nonblock,
+						   flags, addr_len);
+			goto out;
+		}
+		if (err) {
+			ret = err;
+			goto out;
+		}
+		copied = -EAGAIN;
+	}
+	ret = copied;
+out:
+	release_sock(sk);
+	sk_psock_put(sk, psock);
+	return ret;
+}
+
 static struct proto *unix_prot_saved __read_mostly;
 static DEFINE_SPINLOCK(unix_prot_lock);
 static struct proto unix_bpf_prot;
@@ -13,6 +61,7 @@  static void unix_bpf_rebuild_protos(struct proto *prot, const struct proto *base
 {
 	*prot        = *base;
 	prot->close  = sock_map_close;
+	prot->recvmsg = unix_dgram_bpf_recvmsg;
 }
 
 static void unix_bpf_check_needs_rebuild(struct proto *ops)